dsh-npm

dsh-npm is a skill for Claude Code, Codex from Rimagination/scansci-pdf. It costs 81 tokens per session (3,500 once invoked), scanned A, original, MIT.

A guide for packaging an MCP server or agent plugin as a DeepSeek Harness bundle and publishing it as an npm package. MCP is a standard way for an AI assistant to call external tools; npm is a registry for JavaScript packages.

In plain words
What is it for?
Use it to adapt a skill or MCP server to DSH, create the bundle files, include skills and optional metadata, publish the package, or debug installation and loading problems.
Why use it?
It explains the files, metadata, and package contents needed for DSH to install and load the plugin correctly. It also helps diagnose packages that install but fail at runtime.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is '../skill/SKILL.md', // 仓库开发时的规范源文件.

Good fit Use it to adapt a skill or MCP server to DSH, create the bundle files, include skills and optional metadata, publish the package, or debug installation and loading problems.

Compare 6 skills from other repositories ↓
About the project

Rimagination/scansci-pdf is an agent-oriented tool that finds and downloads academic papers from sources such as open-access repositories, preprint services, publishers, and institutional access routes. It accepts identifiers or literature lists, saves papers as named PDF files, and can also export citations or convert PDFs to Markdown. Its MCP server and agent plugins let coding agents use these paper-retrieval workflows.

Rimagination/scansci-pdf · 1,153 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Rimagination/scansci-pdf
agentmods
npx agentmods add skills/rimagination/scansci-pdf/dsh-npm

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dsh-npm

README.md
[![agentmods](https://agentmods.dev/badge/skills/rimagination/scansci-pdf/dsh-npm/github.svg)](https://agentmods.dev/skills/rimagination/scansci-pdf/dsh-npm)
Your own site
<a href="https://agentmods.dev/skills/rimagination/scansci-pdf/dsh-npm"><img src="https://agentmods.dev/badge/skills/rimagination/scansci-pdf/dsh-npm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dsh-npm

Your own site · 80×15
<a href="https://agentmods.dev/skills/rimagination/scansci-pdf/dsh-npm"><img src="https://agentmods.dev/badge/skills/rimagination/scansci-pdf/dsh-npm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.03500
Opus 5.5 $0.00032 $0.01400
Sonnet 5.5 $0.00016 $0.00700
Haiku 4.5 $0.00008 $0.00350

Measured 2d ago against content hash b7083f66d1b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dsh-npm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/dsh-npm/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DSH 插件适配与 npm 发布

目标

产出一个 name@version,在 registry.npmjs.org 上可安装;用户在 DSH 的 Plugins → Add plugin 里只填包名(或 包名@版本)就能得到:

  • 一个 stdio MCP server,工具以 mcp__<serverName>__<tool> 暴露;
  • 一个或多个 skill,出现在会话技能目录;
  • 可选的 bundle 标题、描述、图标。

DSH 的 Add plugin 支持四种来源:npm 包名、Git 地址、tarball URL、本地绝对路径。npm 包名只是其中一种,但它是第三方安装体验最好的一种。

先做三个决定

问题 建议
只注册 skill,还是要连 MCP server? 只要 skill:一个 Host 插件行即可;要 MCP:再加 @deepseek-ai/dsh-mcp-client 行
包名用无 scope 还是 @scope/name? 无 scope 最容易让用户输入;先 npm view <name> version,404 只表示当前可用,不保留
包和 Python/CLI 同版本吗? 是。DSH bundle 只装注册层,CLI 仍要用户自己安装;版本对齐便于排障

目录骨架

dsh-plugin/
  package.json
  cordis.patch.yml
  index.js
  locale/en.json
  locale/zh.json
  icon.png                 # 可选,128x128 PNG
  skills/
    my-skill/SKILL.md      # npm 包内必须自包含
  scripts/sync-skills.mjs  # 从仓库其他位置复制 skill
  README.md
  LICENSE

README.md 和 LICENSE 会被 npm 默认/显式打包;skills/ 必须写进 files。

1. package.json

最小可用字段:

{
  "name": "my-plugin",
  "version": "1.0.0",
  "description": "DeepSeek Harness bundle for ...",
  "type": "module",
  "license": "Apache-2.0",
  "exports": {
    ".": "./index.js",
    "./locale/*.json": "./locale/*.json",
    "./icon": "./icon.png",
    "./package.json": "./package.json"
  },
  "files": [
    "index.js",
    "cordis.patch.yml",
    "locale/*.json",
    "icon.png",
    "README.md",
    "LICENSE",
    "skills/**"
  ],
  "scripts": {
    "sync-skills": "node scripts/sync-skills.mjs",
    "check-skills": "node scripts/sync-skills.mjs --check",
    "prepack": "node scripts/sync-skills.mjs"
  },
  "publishConfig": { "access": "public" },
  "dsh": { "bundle": { "patch": "./cordis.patch.yml" } }
}

关键点:

  • 不要 private: true;它会让 npm publish 直接失败。
  • dsh.bundle.patch 必须指向包内文件,且该文件必须在 files 里,否则装完 DSH 找不到 bundle。
  • exports 至少暴露 ".";locale 和 icon 用于 UI 显示。./package.json 便于工具读取清单。
  • prepack 在 npm pack / npm publish 前运行,生成的文件会进入 tarball;从 registry 安装时不会再次运行。
  • publishConfig.access: public 避免 scoped 包默认 private。

Read the full file on GitHub · 290 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 290 lines · 81 tokens per session scan A b7083f66d1b6

Subscribe to this mod's changes

dsh-npm is a skill published in the GitHub repository Rimagination/scansci-pdf (1,153 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 3,500 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.

microsoft/vscode · 53 tokens